Skip to content

Advertisement

  • Poster presentation
  • Open Access

Correcting for selection bias in two-stage trials with multiple correlated outcomes: application to seamless phase ii/iii clinical trials

  • David Robertson1,
  • A Toby Prevost2 and
  • Jack Bowden1
Trials201516(Suppl 2):P145

https://doi.org/10.1186/1745-6215-16-S2-P145

Published: 16 November 2015

Keywords

Public HealthClinical TrialSimulation StudySelection BiasStandardise Treatment

The problem of selection bias has long been recognised in the analysis of two-stage trials, where promising candidates are selected in stage 1 for confirmatory analysis in stage 2. To efficiently correct for bias, uniformly minimum variance conditionally unbiased estimators (UMVCUEs) have been proposed for a wide variety of trial settings, but where the populations are assumed to be independent. We relax this assumption and derive the UMCVUE in the multivariate normal setting with an arbitrary known covariance structure.

We explore the application of our estimator to two-stage adaptive seamless phase II/III clinical trials. In stage 1, multiple experimental treatments are simultaneously compared with a control. The one that shows the highest standardised treatment difference is then selected for confirmatory analysis in stage. Our UMVCUE allows for unequal number of subjects allocated to each treatment in stage 1, and different (known) treatment variances. We demonstrate the use of our estimator in simulation studies, and show the gain in efficiency over just using the stage 2 data.

Authors’ Affiliations

(1)
MRC Biostatistics Unit, Cambridge, UK
(2)
King's College, London, UK

Copyright

© Robertson et al. 2015

This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.

Comments

By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate. Please note that comments may be removed without notice if they are flagged by another user or do not comply with our community guidelines.

Advertisement